Senior GenAI & Agentic AI Engineer
Persistent
Persistent
Join Persistent as a Senior GenAI & Agentic AI Engineer and drive innovation in AI-led digital engineering. This role focuses on designing, building, and deploying enterprise-grade AI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks. You will leverage your expertise in Python, AI orchestration, vector databases, and enterprise AI integration to create intelligent applications and autonomous AI agents. Help market leaders transform their industries with cutting-edge AI technologies.
Lead the design and development of enterprise AI applications leveraging LLMs and Generative AI. Build and implement end-to-end RAG pipelines, including ingestion, embedding, indexing, and response generation. Design and optimize retrieval strategies for semantic search and contextual relevance. Develop MCP connectors for agent-callable tools. Implement Agentic AI workflows for planning, reasoning, and task execution. Contribute to AI orchestration frameworks integrating RAG, MCP tools, and enterprise platforms. Develop scalable AI services and backend systems. Collaborate with stakeholders to translate business needs into technical solutions. Drive prompt engineering, model tuning, and AI optimization. Build proof-of-concepts and reusable AI components. Ensure security, governance, and compliance in AI applications. Support AI workload deployment in cloud-native environments. Conduct technical reviews and establish AI engineering best practices. Mentor engineering teams and provide technical leadership. Stay updated with advancements in LLMs and Agentic AI.
This role requires 6-10 years of software or AI engineering experience, with a minimum of 3 years focused on Generative AI and LLM solutions. Proficiency in Python programming and strong software engineering practices are essential. A good understanding of C++ development and integrations is beneficial. Experience building enterprise-scale AI applications, intelligent assistants, and end-to-end RAG architectures is crucial. Expertise with AI orchestration frameworks like LlamaIndex or LangChain, and Agentic AI workflows is expected. Familiarity with vector databases such as Pinecone and semantic search implementations is required. Strong understanding of prompt engineering, LLM optimization, and integrating AI with enterprise systems is necessary. Knowledge of software design patterns, scalability principles, and distributed architectures is important. Excellent troubleshooting, debugging, and performance optimization skills are vital.
Persistent Systems
Digital Engineering